Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3214 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6069. Min Range: -10.6069
Max Act: 10.6069. Min Act: -0.1700
Data Index: 7140824 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6069. Min Range: -10.6069
Max Act: 10.4819. Min Act: -0.1700
Data Index: 330734 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6069. Min Range: -10.6069
Max Act: 10.5444. Min Act: -0.1700
Data Index: 5889936 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6069. Min Range: -10.6069
Max Act: 10.2944. Min Act: -0.1700
Data Index: 5794755 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6069. Min Range: -10.6069
Max Act: 10.2944. Min Act: -0.1700
Data Index: 3259363 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6069. Min Range: -10.6069
Max Act: 10.2319. Min Act: -0.1700
Data Index: 8088112 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6069. Min Range: -10.6069
Max Act: 10.1694. Min Act: -0.1698
Data Index: 2850926 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6069. Min Range: -10.6069
Max Act: 10.1069. Min Act: -0.1700
Data Index: 5649715 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6069. Min Range: -10.6069
Max Act: 10.1069. Min Act: -0.1700
Data Index: 7286774 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6069. Min Range: -10.6069
Max Act: 10.1694. Min Act: -0.1700
Data Index: 2811302 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6069. Min Range: -10.6069
Max Act: 10.1069. Min Act: -0.1700
Data Index: 1593254 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6069. Min Range: -10.6069
Max Act: 10.1069. Min Act: -0.1700
Data Index: 6213989 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6069. Min Range: -10.6069
Max Act: 10.0444. Min Act: -0.1700
Data Index: 679857 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6069. Min Range: -10.6069
Max Act: 10.0444. Min Act: -0.1700
Data Index: 5287045 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6069. Min Range: -10.6069
Max Act: 9.9819. Min Act: -0.1700
Data Index: 4509036 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6069. Min Range: -10.6069
Max Act: 9.9819. Min Act: -0.1700
Data Index: 7628092 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6069. Min Range: -10.6069
Max Act: 9.9194. Min Act: -0.1700
Data Index: 7698455 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6069. Min Range: -10.6069
Max Act: 9.9194. Min Act: -0.1700
Data Index: 4775721 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6069. Min Range: -10.6069
Max Act: 9.9194. Min Act: -0.1700
Data Index: 1472842 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6069. Min Range: -10.6069
Max Act: 9.9194. Min Act: -0.1700
Data Index: 2283069 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19